338 lines
8.8 KiB
C++
338 lines
8.8 KiB
C++
/*
|
|
* This file is a part of PikoTools
|
|
* and is distributed under the 2-Clause BSD licence.
|
|
* Author: Tomasz Sowa <t.sowa@ttmath.org>
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2012-2022, Tomasz Sowa
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions are met:
|
|
*
|
|
* 1. Redistributions of source code must retain the above copyright notice,
|
|
* this list of conditions and the following disclaimer.
|
|
*
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
|
|
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
* POSSIBILITY OF SUCH DAMAGE.
|
|
*
|
|
*/
|
|
|
|
#ifndef headerfile_pikotools_src_space_spaceparser
|
|
#define headerfile_pikotools_src_space_spaceparser
|
|
|
|
#include <fstream>
|
|
#include "space.h"
|
|
#include "convert/baseparser.h"
|
|
|
|
|
|
|
|
namespace pt
|
|
{
|
|
|
|
|
|
|
|
|
|
class SpaceParser : public BaseParser
|
|
{
|
|
public:
|
|
|
|
|
|
/*
|
|
ctor -- setting default values (SetDefault() method)
|
|
*/
|
|
SpaceParser();
|
|
|
|
|
|
/*
|
|
status of parsing
|
|
ok - input stream has been parsed correctly
|
|
cant_open_file - I cannot open the file (returns only in a case when parsing a file)
|
|
syntax_error - a syntax error in the input stream
|
|
limit_object_items_exceeded - limit of object items has been exceeded
|
|
limit_table_items_exceeded - limit of table items has been exceeded
|
|
limit_all_items_exceeded - limit of items (key/value pairs of objects or table items) throughout the whole tree has been exceeded
|
|
limit_nested_level_exceeded - limit of nested objects/tables has been exceeded
|
|
*/
|
|
enum Status {
|
|
ok,
|
|
cant_open_file,
|
|
syntax_error,
|
|
limit_object_items_exceeded,
|
|
limit_table_items_exceeded,
|
|
limit_all_items_exceeded,
|
|
limit_nested_level_exceeded
|
|
};
|
|
|
|
|
|
/*
|
|
the last status of parsing, set by parse() methods
|
|
*/
|
|
Status status;
|
|
|
|
|
|
|
|
|
|
/*
|
|
main methods used to parse a JSON file
|
|
file_name is the path to a file
|
|
*/
|
|
Status parse_json_file(const char * file_name, Space & out_space, bool clear_space = true);
|
|
Status parse_json_file(const std::string & file_name, Space & out_space, bool clear_space = true);
|
|
Status parse_json_file(const wchar_t * file_name, Space & out_space, bool clear_space = true);
|
|
Status parse_json_file(const std::wstring & file_name, Space & out_space, bool clear_space = true);
|
|
|
|
|
|
/*
|
|
main methods used to parse a Space file
|
|
file_name is the path to a file
|
|
*/
|
|
Status parse_space_file(const char * file_name, Space & out_space, bool clear_space = true);
|
|
Status parse_space_file(const std::string & file_name, Space & out_space, bool clear_space = true);
|
|
Status parse_space_file(const wchar_t * file_name, Space & out_space, bool clear_space = true);
|
|
Status parse_space_file(const std::wstring & file_name, Space & out_space, bool clear_space = true);
|
|
|
|
|
|
/*
|
|
main methods used to parse
|
|
str - input string (either 8bit ascii or UTF-8 -- see UTF8() method)
|
|
*/
|
|
Status parse_json(const char * str, Space & out_space, bool clear_space = true);
|
|
Status parse_json(const std::string & str, Space & out_space, bool clear_space = true);
|
|
|
|
/*
|
|
main methods used to parse
|
|
here input string is always in unicode (wide characters)
|
|
*/
|
|
Status parse_json(const wchar_t * str, Space & out_space, bool clear_space = true);
|
|
Status parse_json(const std::wstring & str, Space & out_space, bool clear_space = true);
|
|
|
|
Status parse_json(const pt::TextStream & str, Space & out_space, bool clear_space = true);
|
|
Status parse_json(const pt::WTextStream & str, Space & out_space, bool clear_space = true);
|
|
|
|
|
|
Status parse_space(const char * str, Space & out_space, bool clear_space = true);
|
|
Status parse_space(const std::string & str, Space & out_space, bool clear_space = true);
|
|
Status parse_space(const wchar_t * str, Space & out_space, bool clear_space = true);
|
|
Status parse_space(const std::wstring & str, Space & out_space, bool clear_space = true);
|
|
|
|
Status parse_space(const pt::TextStream & str, Space & out_space, bool clear_space = true);
|
|
Status parse_space(const pt::WTextStream & str, Space & out_space, bool clear_space = true);
|
|
|
|
|
|
/*
|
|
* add two args parse method
|
|
* Status parse(const char * str, Space & output_space);
|
|
*
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
* if true then the input file or string (char* or std::string) is treated as UTF-8
|
|
* default true
|
|
*
|
|
* the internal storage for strings is std::wstring so if you call set_utf8(false) then
|
|
* the characters of input string will be simple static_cast<> from char to wchar_t
|
|
*
|
|
*/
|
|
void use_utf8(bool utf);
|
|
|
|
|
|
/*
|
|
*
|
|
* returns a number of a last parsed line
|
|
* can be used to obtain the line in which there was a syntax error
|
|
*
|
|
*/
|
|
int get_last_parsed_line();
|
|
int get_last_parsed_column();
|
|
|
|
|
|
/*
|
|
* get/set limit of object items in one object
|
|
* default: 0 (disabled)
|
|
*/
|
|
void set_object_items_limit(size_t val);
|
|
size_t get_object_items_limit();
|
|
|
|
|
|
/*
|
|
* get/set limit of items in one table
|
|
* default: 0 (disabled)
|
|
*
|
|
*/
|
|
void set_table_items_limit(size_t val);
|
|
size_t get_table_items_limit();
|
|
|
|
|
|
/*
|
|
* get/set limit of all items (objects items and table items) througout the whole tree
|
|
* default: 0 (disabled)
|
|
*
|
|
*/
|
|
void set_all_items_limit(size_t val);
|
|
size_t get_all_items_limit();
|
|
|
|
|
|
/*
|
|
* get/set nested level limit
|
|
* limit of nested objects and tables
|
|
* default: 0 (disabled)
|
|
*
|
|
*/
|
|
void set_nested_level_limit(size_t val);
|
|
size_t get_nested_level_limit();
|
|
|
|
|
|
|
|
|
|
private:
|
|
|
|
|
|
/*
|
|
current space set by SetSpace();
|
|
*/
|
|
Space * root_space;
|
|
|
|
|
|
/*
|
|
last read token
|
|
*/
|
|
std::wstring token;
|
|
|
|
|
|
/*
|
|
separator between a variable and a value, default: '='
|
|
*/
|
|
int separator;
|
|
|
|
|
|
/*
|
|
space starting character, default: '{'
|
|
*/
|
|
int space_start;
|
|
|
|
|
|
/*
|
|
space ending character, default: '}'
|
|
*/
|
|
int space_end;
|
|
|
|
|
|
/*
|
|
table starting character, default: '['
|
|
*/
|
|
int table_start;
|
|
|
|
|
|
/*
|
|
table ending character, default: ']'
|
|
*/
|
|
int table_end;
|
|
|
|
|
|
/*
|
|
option delimiter, default: ','
|
|
*/
|
|
int option_delimiter;
|
|
|
|
|
|
/*
|
|
true if the lastc was escaped (with a backslash)
|
|
we have to know if the last sequence was \" or just "
|
|
*/
|
|
bool char_was_escaped;
|
|
|
|
|
|
/*
|
|
* if parsing_space is false then it means we are parsing JSON format
|
|
*
|
|
*/
|
|
bool parsing_space;
|
|
|
|
|
|
/*
|
|
* object_items_limit - limit of key/value pairs of one object
|
|
* table_items_limit - limit of items of one table
|
|
* all_items_limit - limit of all items of all objects and all tables
|
|
* nested_levels_limit - limit of nested objects/tables
|
|
*/
|
|
size_t object_items_limit;
|
|
size_t table_items_limit;
|
|
size_t all_items_limit;
|
|
size_t nested_levels_limit;
|
|
|
|
/*
|
|
* current_items_counter - how many items (key/value pairs of objects or table items) throughout the whole tree
|
|
* current_nested_level - current nested level of objects and tables
|
|
*/
|
|
size_t current_items_counter;
|
|
size_t current_nested_level;
|
|
|
|
void parse_root_space(bool clear_root_space);
|
|
void parse(Space * space, bool is_object_value, bool is_table_value);
|
|
void parse_space(Space * space);
|
|
void parse_table(Space * space);
|
|
|
|
void parse_key_value_pairs(Space * space);
|
|
void parse_values_list(Space * space);
|
|
|
|
void read_key();
|
|
|
|
void parse_text_value(Space * space);
|
|
void parse_integer_value(Space * space);
|
|
void parse_floating_point_value(Space * space);
|
|
|
|
bool is_alfa_numeric_char(int c);
|
|
|
|
void read_token_until_delimiter(std::wstring & token, int delimiter1, int delimiter2);
|
|
void read_alfa_numeric_token(std::wstring & token);
|
|
void read_string_value(std::wstring & token, bool is_object_value, bool is_table_value);
|
|
|
|
bool is_integer_token();
|
|
bool is_floating_point_token();
|
|
|
|
void read_space_field_token(std::wstring & token);
|
|
void read_token_quoted(std::wstring & token);
|
|
void read_multiline_token_quoted(std::wstring & token);
|
|
|
|
int read_char();
|
|
bool is_white(int c);
|
|
void skip_line();
|
|
void skip_white();
|
|
void trim_last_white(std::wstring & s);
|
|
bool is_hex_digit(wchar_t c);
|
|
int hex_to_int(wchar_t c);
|
|
|
|
bool read_unicode_four_digit_format(bool has_first_byte, int first_byte);
|
|
void read_unicode_json_format(bool has_first_byte, int first_byte);
|
|
void read_unicode_floating_format();
|
|
void read_unicode_code_point();
|
|
|
|
void prepare_to_parsing();
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
} // namespace
|
|
|
|
|
|
#endif
|